Sweaterdog
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -45,6 +45,15 @@ Andy-3.5-preview was made to test the intelligence of a Minecraft Ai with the cu
|
|
45 |
DO NOT expect this model to be able to do everything perfectly, it only knows as much as the dataset told it, as well as the other 2/3 of the untouched parameters allow.
|
46 |
The model *may* experience bugs, such as not saying your name, getting previous messages confused, or other small things.
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
## Safety and FAQ
|
49 |
|
50 |
Q: Is this model safe to use?
|
|
|
45 |
DO NOT expect this model to be able to do everything perfectly, it only knows as much as the dataset told it, as well as the other 2/3 of the untouched parameters allow.
|
46 |
The model *may* experience bugs, such as not saying your name, getting previous messages confused, or other small things.
|
47 |
|
48 |
+
# What models can I choose?
|
49 |
+
|
50 |
+
There are going to be 3 model sizes avaliable, Regular, Mini, and Teensy
|
51 |
+
* Regular is a 7B parameter model, tuned from [Deepseek-R1 Distilled](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
|
52 |
+
* Mini is a 1.5B parameter model, also tuned from [Deepseek-R1 Distilled](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)
|
53 |
+
* Teensy is a tiny little 360M parameter model, trained from [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct)
|
54 |
+
|
55 |
+
Out of all of the models, Teensy had the largest percent of parameters tuned, being 1/2 the models total size
|
56 |
+
|
57 |
## Safety and FAQ
|
58 |
|
59 |
Q: Is this model safe to use?
|